Smart Erasure Brush

1. A method for erasing a feature from a digital image, comprising: identifying a plurality of tip regions on the digital image each covering a portion of the feature; defining an erasure color, the erasure color being variable and potentially changing with each tip region, processing the tip regions to erase the feature including determining an erasure color for the tip region, applying an erasure function to each pixel in the region to remove the feature from the pixel, and decontaminating each pixel in the region including removing a contribution of the erasure color from the pixel color if the pixel color is distinct from the erasure color.

2. A method for erasing a feature from a digital image, comprising: identifying a plurality of tip regions on the digital image each covering a portion of the feature; defining a color match function to be applied to pixels in a tip region, the color match function being variable and potentially changing with each tip region, processing the tip regions to erase the feature including determining an erasure color for the tip region, applying an erasure function to each pixel in the region to remove the feature from the pixel, and decontaminating each pixel in the region including applying the color match function for the tip region to the pixel to remove a contribution of the erasure color from the pixel color if the pixel color is distinct from the erasure color.

3. A method for erasing a feature from a digital image, comprising: identifying a plurality of tip regions on the digital image each covering a portion of the feature to be erased; and processing the tip regions sequentially to erase the feature including applying an erasure function to each pixel in the region to remove the feature from a target pixel where the action of applying the erasure function is given effect in the image before subsequent tip regions are processed, and decontaminating each pixel in the region including removing a contribution of an erasure color from the pixel color if the pixel color is distinct from the erasure color.

4. The method of claim 3 , wherein the step of applying the erasure function includes applying the erasure function at 100 percent to all pixels in the region having a color approximately equal to the erasure color, determining a color difference for all remaining pixels in the region and applying the erasure function at zero percent to all pixels having a color difference above a threshold value.

5. The method of claim 3 , further comprising: applying a stroke using a brush to the digital image to designate a portion of the digital image for processing.

6. The method of claim 3 , wherein the step of determining an erasure color includes sampling a color at a center region of a current brush tip of the brush stroke.

7. The method of claim 3 , wherein the step of determining an erasure color includes sampling a color at a beginning of a brush stroke.

8. The method of claim 3 , wherein the step of determining a background color designates a fixed color for the erasure color.

9. The method of claim 3 , further comprising adjusting a shape of the brush to size a tip region such that the stroke includes a portion of a boundary defining the intersection of the foreground and the background images.

10. The method of claim 9 , wherein the shape of the brush is a circle and the step of adjusting the shape for the brush includes varying a radius of the circle.

11. The method of claim 3 , wherein the threshold is adjustable at each tip application.

12. The method of claim 3 , wherein the step of erasing includes changing alpha values associated with a given pixel.

13. The method of claim 3 , wherein the step of determining a color match value includes determining a difference between the erasure color and the color of the target pixel and applying a function to the difference.

14. The method of claim 13 , wherein the function is a tent function.

15. The method of claim 3 , further including pinning the color match value to reflect colors available in a color space for the digital image.

16. The method of claim 3 , wherein the color match value is adjusted by a density value for the brush.

17. The method of claim 3 , wherein the color match value is reduced by a scaling factor proportional to a distance of the given target pixel from a center of a tip region.

18. The method of claim 3 , wherein the color match value at a target pixel is driven to a minimum value if a target pixel between the current target pixel and a center of a tip region has color match value that is the minimum value.

19. The method of claim 3 , wherein the color match value at a target pixel is driven to a minimum value if all paths between a center of a tip application region and the target pixel include a pixel with a color match value that is the minimum value.

20. The method of claim 3 , wherein the raster data includes data in a plurality of color planes and a color match value is determined for each color plane.

21. The method of claim 3 , wherein the minimum color match value for all the color planes is used to determine whether or not a target pixel is completely or partially erased.

22. The method of claim 3 , wherein the erasure color and the color of a target pixel include alpha channel values, the method further comprising determining a color match value from the alpha channel values.

23. The method of claim 3 , wherein the color values of the erasure color and the target pixels are in a first color space, the method further comprising changing color values for the erasure color and the color of the target pixel to a second different color space prior to determining a color match value.

24. The method of claim 3 , wherein the color values of the erasure color and the target pixels are in a first color space, the method further comprising changing color values for the erasure color and the color of the target pixel to a second different color space prior to removing a contribution of a background color.

25. The method of claim 3 , wherein the color values of the erasure color and the target pixels are in a first color space, the method further comprising changing color values for the erasure color and the color of the target pixel to a second different color space prior to determining a color match value and where the step of removing a contribution of a background color includes converting the decontaminated color values back to the first color space.

26. The method of claim 3 , wherein the erasure color is a background color.

27. A computer readable medium encoded with a computer program for erasing a feature from a digital image comprising instructions for causing a computer to: identify a plurality of tip regions on the digital image each covering a portion of the feature; define an erasure color, the erasure color being variable and potentially changing with each tip region, process the tip regions to erase the feature including determine an erasure color for the tip region, apply an erasure function to each pixel in the region to remove the feature from the pixel, and decontaminate each pixel in the region including removing a contribution of the erasure color from the pixel color if the pixel color is distinct from the erasure color.

28. A computer readable medium encoded with a computer program for erasing a feature from a digital image comprising instructions for causing a computer to: identify a plurality of tip regions on the digital image each covering a portion of the feature; define a color match function to be applied to pixels in a tip region, the color match function being variable and potentially changing with each tip region, process the tip regions to erase the feature including determine an erasure color for the tip region, apply an erasure function to each pixel in the region to remove the feature from the pixel, and decontaminate each pixel in the region including applying the color match function for the tip region to the pixel to remove a contribution of the erasure color from the pixel color if the pixel color is distinct from the erasure color.

29. A computer readable medium encoded with a computer program for erasing a feature from a digital image comprising instructions for causing a computer to: identify a plurality of tip regions on the digital image each covering a portion of the feature to be erased; and process the tip regions sequentially to erase the feature including apply an erasure function to each pixel in the region to remove the feature from a target pixel where the action of applying the erasure function is given effect in the image before subsequent tip regions are processed, and decontaminate each pixel in the region including removing a contribution of an erasure color from the pixel color if the pixel color is distinct from the erasure color.

30. The computer readable medium encoded with the computer program of claim 29 , further comprising instructions to: apply a stroke using a brush to the digital image to designate a portion of the digital image for processing.

31. The computer readable medium encoded with the computer program of claim 29 , wherein the instruction to determine an erasure color includes an instruction to sample a color at a center region of a current brush tip of the brush stroke.

32. The computer readable medium encoded with the computer program of claim 29 , wherein the instruction to determine an erasure color includes an instruction to sample a color at a beginning of a brush stroke.

33. The computer readable medium encoded with the computer program of claim 29 , wherein the instruction to determine a background color designates a fixed color for the erasure color.

34. The computer readable medium encoded with the computer program of claim 29 , further comprising instruction to adjust a shape of the brush to size a tip region such that the stroke includes a portion of a boundary defining the intersection of the foreground and the background images.

35. The computer readable medium encoded with the computer program of claim 34 , wherein the shape of the brush is a circle and the instruction to adjust the shape for the brush includes an instruction to vary a radius of the circle.

36. The computer readable medium encoded with the computer program of claim 29 , wherein the threshold is adjustable at each tip application.

37. The computer readable medium encoded with the computer program of claim 29 , wherein the instruction to erase includes an instruction to change alpha values associated with a given pixel.

38. The computer readable medium encoded with the computer program of claim 29 , wherein the instruction to determine a color match value includes instructions to determine a difference between the erasure color and the color of the target pixel and apply a function to the difference.

39. The computer readable medium encoded with the computer program of claim 38 , wherein the function is a tent function.

40. The computer readable medium encoded with the computer program of claim 29 , further including instructions to pin the color match value to reflect colors available in a color space for the digital image.

41. The computer readable medium encoded with the computer program of claim 29 , wherein the color match value is adjusted by a density value for the brush.

42. The computer readable medium encoded with the computer program of claim 29 , wherein the color match value is reduced by a scaling factor proportional to a distance of the given target pixel from a center of a tip region.

43. The computer readable medium encoded with the computer program of claim 29 , wherein the color match value at a target pixel is driven to a minimum value if a target pixel between the current target pixel and a center of a tip region has color match value that is the minimum value.

44. The computer readable medium encoded with the computer program of claim 29 , wherein the color match value at a target pixel is driven to a minimum value if all paths between a center of a tip application region and the target pixel include a pixel with a color match value that is the minimum value.

45. The computer readable medium encoded with the computer program of claim 29 , wherein the raster data includes data in a plurality of color planes and a color match value is determined for each color plane.

46. The computer readable medium encoded with the computer program of claim 45 , wherein the minimum color match value for all the color planes is used to determine whether or not a target pixel is completely or partially erased.

47. The computer readable medium encoded with the computer program of claim 29 , wherein the erasure color and the color of a target pixel include alpha channel values, the computer program further comprising instructions to determine a color match value from the alpha channel values.

48. The computer readable medium encoded with the computer program of claim 29 , wherein the color values of the erasure color and the target pixels are in a first color space, the computer program further comprising instructions to change color values for the erasure color and the color of the target pixel to a second different color space prior to determining a color match value.

49. The computer readable medium encoded with the computer program of claim 29 , wherein the color values of the erasure color and the target pixels are in a first color space, the computer program further comprising instructions to change color values for the erasure color and the color of the target pixel to a second different color space prior to removing a contribution of a background color.

50. The computer readable medium encoded with the computer program of claim 29 , wherein the color values of the erasure color and the target pixels are in a first color space, the computer program further comprising instructions to change color values for the erasure color and the color of the target pixel to a second different color space prior to determining a color match value and where the instruction to remove a contribution of a background color includes instructions to convert the decontaminated color values back to the first color space.

51. The computer readable medium encoded with the computer program of claim 29 , wherein the erasure color is background color.